Huashan Chen

Prof. Dr. Huashan Chen


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 August 2023
Verified
Conference Paper
Open access
YWYangyang Wang
Yangyang Wang
XZXiao Zhang
Xiao Zhang
MLMingyi Li
Mingyi Li
TLTian Lan
Tian Lan
HCHuashan Chen
Huashan Chen
Dongxiao YuDongxiao Yu
Dongxiao Yu
In this paper, we propose an adaptive learning paradigm for resource-constrained cross-device federated learning, in which heterogeneous local submodels with varying resources can be jointly trained to produce a global model. Different from existing studies, the submodel structures of different clients are formed by arbitrarily assigned neurons according to their local resources. Along this line, we first design a general resource-adaptive federated learning algorithm, namely RA-Fed, and rigorously prove its convergence with asymptotically optimal rate O(1/√Γ*TQ) under loose assumptions. Furthermore, to address both submodels heterogeneity and data heterogeneity challenges under non-uniform training, we come up with a new server aggregation mechanism RAM-Fed with the same theoretically proved convergence rate. Moreover, we shed light on several key factors impacting convergence, such as minimum coverage rate, data heterogeneity level, submodel induced noises. Finally, we conduct extensive experiments on two types of tasks with three widely used datasets under different experimental settings. Compared with the state-of-the-arts, our methods improve the accuracy up to 10% on average. Particularly, when submodels jointly train with 50% parameters, RAM-Fed achieves comparable accuracy to FedAvg trained with the full model.

23 September 2024 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
XZXiao Zhang
Xiao Zhang
SXShuqing Xu
Shuqing Xu
HCHuashan Chen
Huashan Chen
ZCZekai Chen
Zekai Chen
FZFuzhen Zhuang
Fuzhen Zhuang
Dongxiao YuDongxiao Yu
Dongxiao Yu
The robust multivariate time series anomaly detection can facilitate intelligent decisions and timely maintenance in various kinds of monitor systems. However, the robustness is highly restricted by the stochasticity in multivariate time series, which is summarized as temporal stochasticity and spatial stochasticity specifically. In this paper, we explicitly model the temporal stochasticity variables and the latent graph relationship variables into a unified graphical framework, which can achieve better robustness to dynamicity from both the spatial and temporal perspective. First, within the spatial encoder, every connection exists or not is modeled as a binary stochastic variable, and the graph structure can be learnt automatically. Then, the temporal encoder would embed the highly structured time series into latent stochastic variables to capture both complex temporal dependencies and neighbors information. Moreover, we design a history-future combined anomaly score mechanism with both reconstruction decoder and forecasting decoder to improve the anomaly detection performance. By weighting the historical anomaly factor, the future anomaly factor, and the prediction error of current timestamp, the anomaly detection at current timestamp could be more sensitive to anomaly detection. Finally, extensive experiments on three publicly available anomaly detection datasets demonstrate our proposed method can achieve the best performance in terms of recall and F1 compared with state-of-the-arts baselines.

18 March 2024 in IEEE Transactions on Computers
Verified
Journal Article
Closed access
YLYu Liu
Yu Liu
QLQi Luo
Qi Luo
MXMengbai Xiao
Mengbai Xiao
Dongxiao YuDongxiao Yu
Dongxiao Yu
HCHuashan Chen
Huashan Chen
XCXiuzhen Cheng
Xiuzhen Cheng
Hypergraphs are applicable to various domains such as social contagion, online groups, and protein structures due to their effective modeling of multivariate relationships. However, the increasing size of hypergraphs has led to high computation costs, necessitating efficient acceleration strategies. Existing approaches often require consideration of algorithm-specific issues, making them difficult to directly apply to arbitrary hypergraph processing tasks. In this paper, we propose a compression-array acceleration strategy involving hypergraph reordering to improve memory access efficiency, which can be applied to various hypergraph processing tasks without considering the algorithm itself. We introduce a new metric called closeness to optimize the ordering of vertices and hyperedges in the one-dimensional array representation. Moreover, we present an $\frac{1}{2w}$ -approximation algorithm to obtain the optimal ordering of vertices and hyperedges. We also develop an efficient update mechanism for dynamic hypergraphs. Our extensive experiments demonstrate significant improvements in hypergraph processing performance, reduced cache misses, and reduced memory footprint. Furthermore, our method can be integrated into existing hypergraph processing frameworks, such as Hygra, to enhance their performance.

13 July 2025
Verified
Conference Paper
Open access
FZFei Zhu
Fei Zhu
HCHuashan Chen
Huashan Chen
WZWanqian Zhang
Wanqian Zhang
LWLin Wang
Lin Wang
ZLZheng Lin
Zheng Lin
BLBo Li
Bo Li

27 October 2024
Verified
Conference Paper
Open access
WHWenjie Huang
Wenjie Huang
JCJinfu Chen
Jinfu Chen
HCHuashan Chen
Huashan Chen
ZQZhenyu Qi
Zhenyu Qi
XYXiaojia Yang
Xiaojia Yang
SHSen He
Sen He
Virtual reality (VR) offers unprecedented user experiences across diverse areas. However, few studies have focused on code clone in VR software, though it is a significant factor in the emergence and spread of security vulnerabilities in open-source software. In this work, we conduct the first extensive quantitative empirical analysis of code clone in open-source VR software. We create a dataset of 83 open-source VR projects sourced from GitHub and propose to use multiple metrics to facilitate quantitative analysis. Using the NiCad code clone detection tool, we provide a thorough analysis of code clone in our dataset to tackle five meticulously crafted research questions. Our analysis of the experimental results reveals various insights, enhancing our understanding of VR software and paving the way for future research endeavors.

7 August 2025 in Automated Software Engineering
Verified
Journal Article
Closed access
PDF file
HCHuashan Chen
Huashan Chen
ZHZisheng Huang
Zisheng Huang
YXYifan Xu
Yifan Xu
WHWenjie Huang
Wenjie Huang
XWXuheng Wang
Xuheng Wang
SHSen He
Sen He